KAAPA: Knowledge Aware Answers from PDF Analysis

Nicolas Fauceglia; Mustafa Canim; Alfio Gliozzo; Jennifer J. Liang; Nancy Xin Ru Wang; Douglas Burdick; Nandana Mihindukulasooriya; Vittorio Castelli; Guy Feigenblat; David Konopnicki; Yannis Katsis; Radu Florian; Yunyao Li; Salim Roukos; Avirup Sil

KAAPA: Knowledge Aware Answers from PDF Analysis

Nicolas Fauceglia, Mustafa Canim, Alfio Gliozzo, Jennifer J. Liang, Nancy Xin Ru Wang, Douglas Burdick, Nandana Mihindukulasooriya, Vittorio Castelli, Guy Feigenblat, David Konopnicki, Yannis Katsis, Radu Florian, Yunyao Li, Salim Roukos, Avirup Sil

IBM

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We present KAAPA (Knowledge Aware Answers from PDF Analysis), an integrated solution for machine reading comprehension over both text and tables extracted from PDFs. KAAPA enables interactive question refinement using facets generated from an automatically induced Knowledge Graph. In addition, it provides a concise summary of the supporting evidence for the provided answers by aggregating information across multiple sources. KAAPA can be applied consistently to any collection of documents in English with zero domain adaptation effort. We showcase the use of KAAPA for QA on scientific literature using the COVID-19 Open Research Dataset.

Original language	English
Title of host publication	35th AAAI Conference on Artificial Intelligence, AAAI 2021
Publisher	Association for the Advancement of Artificial Intelligence
Pages	16029-16031
Number of pages	3
ISBN (Electronic)	9781713835974
State	Published - 2021
Externally published	Yes
Event	35th AAAI Conference on Artificial Intelligence, AAAI 2021 - Virtual, Online Duration: 2 Feb 2021 → 9 Feb 2021

Publication series

Name	35th AAAI Conference on Artificial Intelligence, AAAI 2021
Volume	18

Conference

Conference	35th AAAI Conference on Artificial Intelligence, AAAI 2021
City	Virtual, Online
Period	2/02/21 → 9/02/21

Bibliographical note

Publisher Copyright:
Copyright © 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved

Cite this

Fauceglia, N., Canim, M., Gliozzo, A., Liang, J. J., Wang, N. X. R., Burdick, D., Mihindukulasooriya, N., Castelli, V., Feigenblat, G., Konopnicki, D., Katsis, Y., Florian, R., Li, Y., Roukos, S., & Sil, A. (2021). KAAPA: Knowledge Aware Answers from PDF Analysis. In 35th AAAI Conference on Artificial Intelligence, AAAI 2021 (pp. 16029-16031). (35th AAAI Conference on Artificial Intelligence, AAAI 2021; Vol. 18). Association for the Advancement of Artificial Intelligence.

@inproceedings{16a62a2c5b784ef8a04c0d90d2702151,

title = "KAAPA: Knowledge Aware Answers from PDF Analysis",

abstract = "We present KAAPA (Knowledge Aware Answers from PDF Analysis), an integrated solution for machine reading comprehension over both text and tables extracted from PDFs. KAAPA enables interactive question refinement using facets generated from an automatically induced Knowledge Graph. In addition, it provides a concise summary of the supporting evidence for the provided answers by aggregating information across multiple sources. KAAPA can be applied consistently to any collection of documents in English with zero domain adaptation effort. We showcase the use of KAAPA for QA on scientific literature using the COVID-19 Open Research Dataset.",

author = "Nicolas Fauceglia and Mustafa Canim and Alfio Gliozzo and Liang, {Jennifer J.} and Wang, {Nancy Xin Ru} and Douglas Burdick and Nandana Mihindukulasooriya and Vittorio Castelli and Guy Feigenblat and David Konopnicki and Yannis Katsis and Radu Florian and Yunyao Li and Salim Roukos and Avirup Sil",

note = "Publisher Copyright: Copyright {\textcopyright} 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved; 35th AAAI Conference on Artificial Intelligence, AAAI 2021 ; Conference date: 02-02-2021 Through 09-02-2021",

year = "2021",

language = "אנגלית",

series = "35th AAAI Conference on Artificial Intelligence, AAAI 2021",

publisher = "Association for the Advancement of Artificial Intelligence",

pages = "16029--16031",

booktitle = "35th AAAI Conference on Artificial Intelligence, AAAI 2021",

}

Fauceglia, N, Canim, M, Gliozzo, A, Liang, JJ, Wang, NXR, Burdick, D, Mihindukulasooriya, N, Castelli, V, Feigenblat, G, Konopnicki, D, Katsis, Y, Florian, R, Li, Y, Roukos, S & Sil, A 2021, KAAPA: Knowledge Aware Answers from PDF Analysis. in 35th AAAI Conference on Artificial Intelligence, AAAI 2021. 35th AAAI Conference on Artificial Intelligence, AAAI 2021, vol. 18, Association for the Advancement of Artificial Intelligence, pp. 16029-16031, 35th AAAI Conference on Artificial Intelligence, AAAI 2021, Virtual, Online, 2/02/21.

KAAPA: Knowledge Aware Answers from PDF Analysis. / Fauceglia, Nicolas; Canim, Mustafa; Gliozzo, Alfio et al.
35th AAAI Conference on Artificial Intelligence, AAAI 2021. Association for the Advancement of Artificial Intelligence, 2021. p. 16029-16031 (35th AAAI Conference on Artificial Intelligence, AAAI 2021; Vol. 18).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - KAAPA

T2 - 35th AAAI Conference on Artificial Intelligence, AAAI 2021

AU - Fauceglia, Nicolas

AU - Canim, Mustafa

AU - Gliozzo, Alfio

AU - Liang, Jennifer J.

AU - Wang, Nancy Xin Ru

AU - Burdick, Douglas

AU - Mihindukulasooriya, Nandana

AU - Castelli, Vittorio

AU - Feigenblat, Guy

AU - Konopnicki, David

AU - Katsis, Yannis

AU - Florian, Radu

AU - Li, Yunyao

AU - Roukos, Salim

AU - Sil, Avirup

PY - 2021

Y1 - 2021

N2 - We present KAAPA (Knowledge Aware Answers from PDF Analysis), an integrated solution for machine reading comprehension over both text and tables extracted from PDFs. KAAPA enables interactive question refinement using facets generated from an automatically induced Knowledge Graph. In addition, it provides a concise summary of the supporting evidence for the provided answers by aggregating information across multiple sources. KAAPA can be applied consistently to any collection of documents in English with zero domain adaptation effort. We showcase the use of KAAPA for QA on scientific literature using the COVID-19 Open Research Dataset.

AB - We present KAAPA (Knowledge Aware Answers from PDF Analysis), an integrated solution for machine reading comprehension over both text and tables extracted from PDFs. KAAPA enables interactive question refinement using facets generated from an automatically induced Knowledge Graph. In addition, it provides a concise summary of the supporting evidence for the provided answers by aggregating information across multiple sources. KAAPA can be applied consistently to any collection of documents in English with zero domain adaptation effort. We showcase the use of KAAPA for QA on scientific literature using the COVID-19 Open Research Dataset.

UR - http://www.scopus.com/inward/record.url?scp=85130044582&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85130044582

T3 - 35th AAAI Conference on Artificial Intelligence, AAAI 2021

SP - 16029

EP - 16031

BT - 35th AAAI Conference on Artificial Intelligence, AAAI 2021

PB - Association for the Advancement of Artificial Intelligence

Y2 - 2 February 2021 through 9 February 2021

ER -

KAAPA: Knowledge Aware Answers from PDF Analysis

Abstract

Publication series

Conference

Bibliographical note

Other files and links

Fingerprint

Cite this